Genera models

Of the 182 identified genera of importance for deer and elk forage or sage-grouse, we had sufficient data (e.g. at least 3 ecognition polygons) to train models for 153 of the genera

In the vast majority of cases, Random Forest models appeared to train the best predictive models based on RMSE values.

BestModel_RMSE Number of Genera
RF 93
RPART 22
BAGEARTH 11
GBM 11
RPART2 5
TREEBAG 5
XGBOOST 3
GLM 2
GBM,RPART 1

We were able to attain R-squared values of >= 0.2 for 28% of the trained genera models.

R-squared values plotted according to sample size

Data summary of trained models.

Species models

Of the 593 identified species of importance for deer and elk forage or sage-grouse, we had sufficient data (e.g. at least 3 ecognition polygons) to train models for 240 of the species.

In the vast majority of cases, Random Forest models appeared to train the best predictive models based on RMSE values.

BestModel_RMSE Number of Species
RF 126
RPART 35
BAGEARTH 19
GBM 19
XGBOOST 14
TREEBAG 11
LM 9
GLM 4
RPART2 3

We were able to attain R-squared values of >= 0.2 for 21% of the trained species models.

R-squared values plotted according to sample size

Data summary of trained models.

Subspecies models

Of the 216 identified subspecies of importance for deer and elk forage or sage-grouse, we had sufficient data (e.g. at least 3 ecognition polygons) to train models for 11 of the subspecies.

BestModel_RMSE Number of Subspecies
RF 6
GBM 2
TREEBAG 2
RPART 1

We were able to attain R-squared values of >= 0.2 for 64% of the trained subspecies models.

R-squared values plotted according to sample size

Data summary of trained models.